{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:GCDR5EIX3BTRQVJRWZIEMPRHVT","short_pith_number":"pith:GCDR5EIX","canonical_record":{"source":{"id":"2410.21951","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2024-10-29T11:12:01Z","cross_cats_sorted":["cs.AI","cs.SD"],"title_canon_sha256":"150f9505709d2cbb17b0e8bd9b6b0365d37bce2a9b2654dcb1e4ce33ce46d729","abstract_canon_sha256":"f8bf242df2b7012cb45c9c5745a3ce44afda708427b5ba4b9681666fe6666b25"},"schema_version":"1.0"},"canonical_sha256":"30871e9117d867185531b650463e27acfb3acf38bdbe709a57c317a41fe2efe1","source":{"kind":"arxiv","id":"2410.21951","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.21951","created_at":"2026-07-05T10:11:27Z"},{"alias_kind":"arxiv_version","alias_value":"2410.21951v2","created_at":"2026-07-05T10:11:27Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.21951","created_at":"2026-07-05T10:11:27Z"},{"alias_kind":"pith_short_12","alias_value":"GCDR5EIX3BTR","created_at":"2026-07-05T10:11:27Z"},{"alias_kind":"pith_short_16","alias_value":"GCDR5EIX3BTRQVJR","created_at":"2026-07-05T10:11:27Z"},{"alias_kind":"pith_short_8","alias_value":"GCDR5EIX","created_at":"2026-07-05T10:11:27Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:GCDR5EIX3BTRQVJRWZIEMPRHVT","target":"record","payload":{"canonical_record":{"source":{"id":"2410.21951","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2024-10-29T11:12:01Z","cross_cats_sorted":["cs.AI","cs.SD"],"title_canon_sha256":"150f9505709d2cbb17b0e8bd9b6b0365d37bce2a9b2654dcb1e4ce33ce46d729","abstract_canon_sha256":"f8bf242df2b7012cb45c9c5745a3ce44afda708427b5ba4b9681666fe6666b25"},"schema_version":"1.0"},"canonical_sha256":"30871e9117d867185531b650463e27acfb3acf38bdbe709a57c317a41fe2efe1","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:11:27.717140Z","signature_b64":"p1ufK9T8A7fGio43ehupbpCh14/Z+sAQ39Y2exgF51g6Df7AkvYmlgOovkEplA26UG/hKRIaG0pcpljPjfawCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"30871e9117d867185531b650463e27acfb3acf38bdbe709a57c317a41fe2efe1","last_reissued_at":"2026-07-05T10:11:27.716541Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:11:27.716541Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2410.21951","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T10:11:27Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"nNvtQYfZOyFJK3ns9uJt1B6lAb1BVIJHhTav4YFBJXlTqA43bApFPe64iK0XwO0e78Fv0+IIl5HCkvelk3Y2AA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T01:00:21.592594Z"},"content_sha256":"c0e9b5e1ed135a436423968b243cc293796bc56951b365dfd8b2a7b9d156f0d0","schema_version":"1.0","event_id":"sha256:c0e9b5e1ed135a436423968b243cc293796bc56951b365dfd8b2a7b9d156f0d0"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:GCDR5EIX3BTRQVJRWZIEMPRHVT","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Fast and High-Quality Auto-Regressive Speech Synthesis via Speculative Decoding","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.SD"],"primary_cat":"eess.AS","authors_text":"Bohan Li, Hankun Wang, Kai Yu, Situo Zhang, Yiwei Guo","submitted_at":"2024-10-29T11:12:01Z","abstract_excerpt":"The auto-regressive architecture, like GPTs, is widely used in modern Text-to-Speech (TTS) systems. However, it incurs substantial inference time, particularly due to the challenges in the next-token prediction posed by lengthy sequences of speech tokens. In this work, we introduce VADUSA, one of the first approaches to accelerate auto-regressive TTS through speculative decoding. Our results show that VADUSA not only significantly improves inference speed but also enhances performance by incorporating draft heads to predict future speech content auto-regressively. Furthermore, the inclusion of"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.21951","kind":"arxiv","version":2},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2410.21951/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T10:11:27Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"7A0TOZC9vC1ghfj7XPYXdYIMuFd0Ne640ECgmzccyz+oCtp3fSLXgwfajqv1rE4VpyEPlC61WNKrO2ylvt0kDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T01:00:21.593088Z"},"content_sha256":"0d5598f60eb80c712fe0a3a27b17ff8cac01de9d5d62d37f28a36d9557988592","schema_version":"1.0","event_id":"sha256:0d5598f60eb80c712fe0a3a27b17ff8cac01de9d5d62d37f28a36d9557988592"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/GCDR5EIX3BTRQVJRWZIEMPRHVT/bundle.json","state_url":"https://pith.science/pith/GCDR5EIX3BTRQVJRWZIEMPRHVT/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/GCDR5EIX3BTRQVJRWZIEMPRHVT/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-08T01:00:21Z","links":{"resolver":"https://pith.science/pith/GCDR5EIX3BTRQVJRWZIEMPRHVT","bundle":"https://pith.science/pith/GCDR5EIX3BTRQVJRWZIEMPRHVT/bundle.json","state":"https://pith.science/pith/GCDR5EIX3BTRQVJRWZIEMPRHVT/state.json","well_known_bundle":"https://pith.science/.well-known/pith/GCDR5EIX3BTRQVJRWZIEMPRHVT/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:GCDR5EIX3BTRQVJRWZIEMPRHVT","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"f8bf242df2b7012cb45c9c5745a3ce44afda708427b5ba4b9681666fe6666b25","cross_cats_sorted":["cs.AI","cs.SD"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2024-10-29T11:12:01Z","title_canon_sha256":"150f9505709d2cbb17b0e8bd9b6b0365d37bce2a9b2654dcb1e4ce33ce46d729"},"schema_version":"1.0","source":{"id":"2410.21951","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.21951","created_at":"2026-07-05T10:11:27Z"},{"alias_kind":"arxiv_version","alias_value":"2410.21951v2","created_at":"2026-07-05T10:11:27Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.21951","created_at":"2026-07-05T10:11:27Z"},{"alias_kind":"pith_short_12","alias_value":"GCDR5EIX3BTR","created_at":"2026-07-05T10:11:27Z"},{"alias_kind":"pith_short_16","alias_value":"GCDR5EIX3BTRQVJR","created_at":"2026-07-05T10:11:27Z"},{"alias_kind":"pith_short_8","alias_value":"GCDR5EIX","created_at":"2026-07-05T10:11:27Z"}],"graph_snapshots":[{"event_id":"sha256:0d5598f60eb80c712fe0a3a27b17ff8cac01de9d5d62d37f28a36d9557988592","target":"graph","created_at":"2026-07-05T10:11:27Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2410.21951/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The auto-regressive architecture, like GPTs, is widely used in modern Text-to-Speech (TTS) systems. However, it incurs substantial inference time, particularly due to the challenges in the next-token prediction posed by lengthy sequences of speech tokens. In this work, we introduce VADUSA, one of the first approaches to accelerate auto-regressive TTS through speculative decoding. Our results show that VADUSA not only significantly improves inference speed but also enhances performance by incorporating draft heads to predict future speech content auto-regressively. Furthermore, the inclusion of","authors_text":"Bohan Li, Hankun Wang, Kai Yu, Situo Zhang, Yiwei Guo","cross_cats":["cs.AI","cs.SD"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2024-10-29T11:12:01Z","title":"Fast and High-Quality Auto-Regressive Speech Synthesis via Speculative Decoding"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.21951","kind":"arxiv","version":2},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:c0e9b5e1ed135a436423968b243cc293796bc56951b365dfd8b2a7b9d156f0d0","target":"record","created_at":"2026-07-05T10:11:27Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"f8bf242df2b7012cb45c9c5745a3ce44afda708427b5ba4b9681666fe6666b25","cross_cats_sorted":["cs.AI","cs.SD"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2024-10-29T11:12:01Z","title_canon_sha256":"150f9505709d2cbb17b0e8bd9b6b0365d37bce2a9b2654dcb1e4ce33ce46d729"},"schema_version":"1.0","source":{"id":"2410.21951","kind":"arxiv","version":2}},"canonical_sha256":"30871e9117d867185531b650463e27acfb3acf38bdbe709a57c317a41fe2efe1","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"30871e9117d867185531b650463e27acfb3acf38bdbe709a57c317a41fe2efe1","first_computed_at":"2026-07-05T10:11:27.716541Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:11:27.716541Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"p1ufK9T8A7fGio43ehupbpCh14/Z+sAQ39Y2exgF51g6Df7AkvYmlgOovkEplA26UG/hKRIaG0pcpljPjfawCA==","signature_status":"signed_v1","signed_at":"2026-07-05T10:11:27.717140Z","signed_message":"canonical_sha256_bytes"},"source_id":"2410.21951","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c0e9b5e1ed135a436423968b243cc293796bc56951b365dfd8b2a7b9d156f0d0","sha256:0d5598f60eb80c712fe0a3a27b17ff8cac01de9d5d62d37f28a36d9557988592"],"state_sha256":"e9790d3827d7a38b91cf46ed718c7d7a16e01914737ade319fe06833a0628f45"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"oTFWuG/s3Vb1ocYDGXfqg3S/udc595b2l+vzpbPzIaz6jfOhdQtFEvZyg3FW39eIEiwrHfl+LRDan4qJRvzgBw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-08T01:00:21.598846Z","bundle_sha256":"c44b22fb55b9cfad93bb5df5f2b4627274dc069b3f9ec65e74a8cb42df3f97f8"}}